scholarly journals ControlIt! — A Software Framework for Whole-Body Operational Space Control

2016 ◽  
Vol 13 (01) ◽  
pp. 1550040 ◽  
Author(s):  
Chien-Liang Fok ◽  
Gwendolyn Johnson ◽  
John D. Yamokoski ◽  
Aloysius Mok ◽  
Luis Sentis
Keyword(s):  
Upper Body ◽  
Whole Body ◽  
Software Framework ◽  
Physical Constraints ◽  
Lower Priority ◽  
Redundant Robots ◽  
Operational Space ◽  
Floating Base ◽  
Position Task ◽  
Product Disassembly

Whole Body Operational Space Control (WBOSC) enables floating-base highly redundant robots to achieve unified motion/force control of one or more operational space objectives while adhering to physical constraints. It is a pioneering algorithm in the field of human-centered Whole-Body Control (WBC). Although there are extensive studies on the algorithms and theory behind WBOSC, limited studies exist on the software architecture and APIs that enable WBOSC to perform and be integrated into a larger system. In this paper, we address this by presenting ControlIt!, a new open-source software framework for WBOSC. Unlike previous implementations, ControlIt! is multi-threaded to increase maximum servo frequencies using standard PC hardware. A new parameter binding mechanism enables tight integration between ControlIt! and external processes via an extensible set of transport protocols. To support a new robot, only two plugins and a URDF model is needed — the rest of ControlIt! remains unchanged. New WBC primitives can be added by writing Task or Constraint plugins. ControlIt!’s capabilities are demonstrated on Dreamer, a 16-DOF torque controlled humanoid upper body robot containing both series elastic and co-actuated joints, and using it to perform a product disassembly task. Using this testbed, we show that ControlIt! can achieve average servo latencies of about 0.5[Formula: see text]ms when configured with two Cartesian position tasks, two orientation tasks, and a lower priority posture task. This is 10 times faster than the 5[Formula: see text]ms that was achieved using UTA-WBC, the prototype implementation of WBOSC that is both application and platform-specific. Variations in the product’s position is handled by updating the goal of the Cartesian position task. ControlIt!’s source code is released under LGPL and we hope it will be adopted and maintained by the WBC community for the long term as a platform for WBC development and integration.

Multi-Objective Optimization of Human Gait With a Discomfort Function

2016 ◽  
Author(s):  
Hyun-Jung Kwon ◽  
Hyun-Joon Chung ◽  
Yujiang Xiang
Keyword(s):  
Joint Torque ◽  
Upper Body ◽  
Whole Body ◽  
Human Gait ◽  
Multi Objective Optimization ◽  
Joint Angles ◽  
Backward Walking ◽  
Multi Objective ◽  
Body Model ◽  
Neutral Angle

The objective of this study was to develop a discomfort function for including a high DOF upper body model during walking. A multi-objective optimization (MOO) method was formulated by minimizing dynamic effort and the discomfort function simultaneously. The discomfort function is defined as the sum of the squares of deviation of joint angles from their neutral angle positions. The dynamic effort is the sum of the joint torque squared. To investigate the efficacy of the proposed MOO method, backward walking simulation was conducted. By minimizing both dynamic effort and the discomfort function, a 3D whole body model with a high DOF upper body for walking was demonstrated successfully.

Recognition and prediction of driver’s whole body posture model

2022 ◽  
pp. 095440702110686
Author(s):  
Jun Wu ◽  
Jian Liu ◽  
Xiuyuan Li ◽  
Lingbo Yan ◽  
Libo Cao ◽  
...  
Keyword(s):  
Regression Model ◽  
Body Posture ◽  
Upper Body ◽  
Whole Body ◽  
Lower Body ◽  
Key Factor ◽  
Upper Body Posture ◽  
Spatial Coordinates ◽  
Posture Prediction ◽  
Connection Length

The driver’s whole-body posture at the time of a collision is a key factor in determining the magnitude of injury to the driver. However, current researchs on driver posture models only consider the upper body posture of the driver, and the lower body area which is not perceived by sensors is not studied. This paper investigates the driver’s posture and establishes a 3D posture model of the driver’s whole body through the application of machine vision algorithms and regression model statistics. This study proposes an improved Kinect-OpenPose algorithm for identifying the 3D spatial coordinates of nine keypoints of the driver’s upper body. The posture prediction regression model of four keypoints of the lower body is established by conducting volunteer posture acquisition experiments on the developed simulated driving seat and analyzing the volunteer posture data through using the principal components of the upper body keypoints and the seat parameters. The experiments proved that the error of the regression model in this paper is minor than that of current studies, and the accuracy of the keypoint location and the keypoint connection length of the established driver whole body posture model is high, which provides implications for future studies.

scholarly journals Comparative study on the redundancy of mobile single- and dual-arm robots

2016 ◽  
Vol 13 (6) ◽  
pp. 172988141666678
Author(s):  
Hongxing Wang ◽  
Ruifeng Li ◽  
Yunfeng Gao ◽  
Chuqing Cao ◽  
Lianzheng Ge
Keyword(s):  
Rate Control ◽  
Control Algorithm ◽  
Redundant Robot ◽  
Motion Models ◽  
Redundant Robots ◽  
Operational Space ◽  
Rate Control Algorithm ◽  
Simulation Results ◽  
Dual Arm Robot ◽  
Dual Arm

A whole resolved motion rate control algorithm designed for mobile dual-arm redundant robots is presented in this article. Based on this algorithm, the end-effector movements of the dual arms of the mobile dual-arm redundant robot can be decomposed into the movements of the two driving wheels of the differential driving platform and the movements of the dual-arm each joint of this robot harmoniously. The influence of the redundancies of the single- and dual-arm robots on the operation based on the fixed- and differential-driving platforms, which are then based on the whole resolved motion rate control algorithm, is studied after building their motion models. Some comparisons are made to show the advantages of this algorithm on the entire modeling of the complicated robotic system and the influences of the redundancy. First, the comparison of the simulation results between the fixed single-arm robot and the mobile single-arm robot is presented. Second, a comparison of the simulation results between the mobile single-arm robot and the mobile dual-arm robots is shown. Compared with the mobile single-arm robot and the fixed dual-arm robot based on this algorithm, the mobile dual-arm robot has more redundancy and can simultaneously track and operate different objects. Moreover, the mobile dual-arm redundant robot has better smoothness, more flexibility, larger operational space, and more harmonious cooperation between the two arms and the differential driving platform during the entire mobile operational process.

scholarly journals Magnetic Resonance-Compatible Arm-Crank Ergometry: A New Platform Linking Whole-Body Calorimetry to Upper-Extremity Biomechanics and Arm Muscle Metabolism

2020 ◽  
Author(s):  
Riemer JK Vegter ◽  
Sebastiaan van den Brink ◽  
Leonora J Mouton ◽  
Anita Sibeijn-Kuiper ◽  
Lucas H.V. van der Woude ◽  
...  
Keyword(s):  
Magnetic Resonance ◽  
Surface Electromyography ◽  
Motor Units ◽  
Daily Practice ◽  
Muscle Disease ◽  
Upper Body ◽  
Whole Body ◽  
Energetic Efficiency ◽  
The Impact

Abstract Background: Evaluation of the effect of human upper body training regimens may benefit from knowledge of local energy expenditure in arm muscles. To that end, we developed a novel asynchronous arm-crank ergometry platform for use in a clinical magnetic resonance (MR) scanner with 31P spectroscopy capability to study arm muscle energetics. The utility of the platform was tested in an investigation of the impact of daily practice on the energetic efficiency of execution of an arm-cranking task (ACT) in healthy subjects. Results: We recorded the first ever in vivo 31P MR spectra from the human biceps bracii muscle during ACT execution pre- and post-three weeks of daily practice bouts, respectively. Complementary datasets on whole body oxygen consumption, arm muscle electrical activity, arm-force and power output, respectively, were obtained in the mock-up scanner. The mean gross mechanical efficiency of execution of the ACT significantly increased 1.5-fold from 5.7 ± 1.2% to 8.6 ± 1.7% (P<0.05) after training, respectively. However, in only one subject this improvement was associated with recruitment of strictly oxidative motor units in the working biceps muscle. In all other subjects, biceps pH fell below 6.8 during exercise indicating recruitment of anaerobic motor units, the magnitude of which was either unaffected (two subjects) or even increased (two subjects) post-training. Surface electromyography and mechanical force recordings revealed that individuals employed various arm muscle recruitment strategies, using either predominantly elbow flexor muscles (two subjects), elbow extensor muscles (one subject,) or a combination of the two (two subjects), respectively. Three weeks of training improved muscle coordination but did not alter individual strategies. Conclusions: The new platform has produced the first ever in vivo dynamic data on human biceps energy and pH balance during upper body exercise. It allows evaluation of cyclic motor performance and outcomes of upper-body training regimens in healthy novices by integrating these new measurements with whole body calorimetry, surface electromyography and biomechanical measurements. This methodology may be equally valid for lower-limb impaired athletes, wheelchair users and patients with debilitating muscle disease.

scholarly journals SCIPA Full-On: A Randomized Controlled Trial Comparing Intensive Whole-Body Exercise and Upper Body Exercise After Spinal Cord Injury

2018 ◽  
Vol 32 (6-7) ◽  
pp. 557-567 ◽  
Author(s):  
Mary P. Galea ◽  
Sarah A. Dunlop ◽  
Timothy Geraghty ◽  
Glen M. Davis ◽  
Andrew Nunn ◽  
...  
Keyword(s):  
Spinal Cord ◽  
Randomized Controlled Trial ◽  
Adverse Events ◽  
Controlled Trial ◽  
Upper Body ◽  
Whole Body ◽  
Upper Body Exercise ◽  
Randomized Controlled ◽  
Cord Injury ◽  
Full Body

Background. While upper body training has been effective for improving aerobic fitness and muscle strength after spinal cord injury (SCI), activity-based therapies intended to activate the paralyzed extremities have been reported to promote neurological improvement. Objective. To compare the effectiveness of intensive whole-body exercise compared with upper body exercise for people with chronic SCI. Methods. A parallel-group randomized controlled trial was conducted. Participants with a range of SCI levels and severity were randomized to either full-body exercise (FBE) or upper body exercise (UBE) groups (3 sessions per week over 12 weeks). FBE participants underwent locomotor training, functional electrical stimulation-assisted leg cycling, and trunk and lower extremity exercises, while UBE participants undertook upper body strength and aerobic fitness training only. The primary outcome measure was the American Spinal Injury Association (ASIA) motor score for upper and lower extremities. Adverse events were systematically recorded. Results. A total of 116 participants were enrolled and included in the primary analysis. The adjusted mean between-group difference was −0.04 (95% CI −1.12 to 1.04) for upper extremity motor scores, and 0.90 (95% CI −0.48 to 2.27) for lower extremity motor scores. There were 15 serious adverse events in UBE and 16 in FBE, but only one of these was definitely related to the experimental intervention (bilateral femoral condyle and tibial plateau subchondral fractures). No significant between-group difference was found for adverse events, or functional or behavioral variables. Conclusions. Full-body training did not lead to improved ASIA motor scores compared with upper body training in people with chronic SCI.

scholarly journals Garment Categorization Using Data Mining Techniques

Symmetry ◽  
2020 ◽  
Vol 12 (6) ◽  
pp. 984
Author(s):  
Sheenam Jain ◽  
Vijay Kumar
Keyword(s):  
Data Mining ◽  
Supply Chain ◽  
Random Forest ◽  
Good Deal ◽  
Classification Model ◽  
Upper Body ◽  
Whole Body ◽  
Product Data ◽  
Soft Classification ◽  
Using Data

The apparel industry houses a huge amount and variety of data. At every step of the supply chain, data is collected and stored by each supply chain actor. This data, when used intelligently, can help with solving a good deal of problems for the industry. In this regard, this article is devoted to the application of data mining on the industry’s product data, i.e., data related to a garment, such as fabric, trim, print, shape, and form. The purpose of this article is to use data mining and symmetry-based learning techniques on product data to create a classification model that consists of two subsystems: (1) for predicting the garment category and (2) for predicting the garment sub-category. Classification techniques, such as Decision Trees, Naïve Bayes, Random Forest, and Bayesian Forest were applied to the ‘Deep Fashion’ open-source database. The data contain three garment categories, 50 garment sub-categories, and 1000 garment attributes. The two subsystems were first trained individually and then integrated using soft classification. It was observed that the performance of the random forest classifier was comparatively better, with an accuracy of 86%, 73%, 82%, and 90%, respectively, for the garment category, and sub-categories of upper body garment, lower body garment, and whole-body garment.

scholarly journals Measurement of Human Gait Symmetry using Body Surface Normals Extracted from Depth Maps

Sensors ◽  
2019 ◽  
Vol 19 (4) ◽  
pp. 891 ◽  
Author(s):  
Trong-Nguyen Nguyen ◽  
Huu-Hung Huynh ◽  
Jean Meunier
Keyword(s):  
Body Surface ◽  
Lower Limbs ◽  
Upper Body ◽  
Whole Body ◽  
Human Gait ◽  
Gait Symmetry ◽  
Symmetry Index ◽  
Depth Maps ◽  
Abnormal Gait ◽  
3D Information

In this paper, we introduce an approach for measuring human gait symmetry where the input is a sequence of depth maps of subject walking on a treadmill. Body surface normals are used to describe 3D information of the walking subject in each frame. Two different schemes for embedding the temporal factor into a symmetry index are proposed. Experiments on the whole body, as well as the lower limbs, were also considered to assess the usefulness of upper body information in this task. The potential of our method was demonstrated with a dataset of 97,200 depth maps of nine different walking gaits. An ROC analysis for abnormal gait detection gave the best result ( AUC = 0.958 ) compared with other related studies. The experimental results provided by our method confirm the contribution of upper body in gait analysis as well as the reliability of approximating average gait symmetry index without explicitly considering individual gait cycles for asymmetry detection.

scholarly journals Joint Pedestrian and Body Part Detection via Semantic Relationship Learning

2019 ◽  
Vol 9 (4) ◽  
pp. 752 ◽  
Author(s):  
Junhua Gu ◽  
Chuanxin Lan ◽  
Wenbai Chen ◽  
Hu Han
Keyword(s):  
Pedestrian Detection ◽  
Body Part ◽  
Upper Body ◽  
Whole Body ◽  
Body Parts ◽  
Semantic Relationship ◽  
The Public ◽  
Novel Approach ◽  
In The Wild ◽  
Person Search

While remarkable progress has been made to pedestrian detection in recent years, robust pedestrian detection in the wild e.g., under surveillance scenarios with occlusions, remains a challenging problem. In this paper, we present a novel approach for joint pedestrian and body part detection via semantic relationship learning under unconstrained scenarios. Specifically, we propose a Body Part Indexed Feature (BPIF) representation to encode the semantic relationship between individual body parts (i.e., head, head-shoulder, upper body, and whole body) and highlight per body part features, providing robustness against partial occlusions to the whole body. We also propose an Adaptive Joint Non-Maximum Suppression (AJ-NMS) to replace the original NMS algorithm widely used in object detection, leading to higher precision and recall for detecting overlapped pedestrians. Experimental results on the public-domain CUHK-SYSU Person Search Dataset show that the proposed approach outperforms the state-of-the-art methods for joint pedestrian and body part detection in the wild.

Sign in / Sign up

Export Citation Format

Share Document